© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93077
    Prev
    Next
    INDEX
    Explanations

    cursor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.84
     HasFactory
    -0.84
    tagHelperRunner
    -0.84
    ReusableCell
    -0.81
     nahilalakip
    -0.75
    fjspx
    -0.74
    ViewImports
    -0.73
    
    -0.72
     autorytatywna
    -0.71
    دانشنامهٔ
    -0.70
    POSITIVE LOGITS
     position
    0.58
     location
    0.53
    positor
    0.51
     of
    0.49
    กระท
    0.47
    fromCharCode
    0.47
     authority
    0.47
    </table>
    0.46
     loc
    0.45
     месте
    0.45
    Activations Density 0.012%

    No Known Activations